An Efficient Method to Predict Student Education Performance using GoogleNet compared with InceptionNet

Ultimately, the project aims to show that GoogleNet can be a more accurate predictor of students' performance in the classroom than InceptionNet. Steps and Resources: In this study, we look at GoogleNet and InceptionNet side by side. A total of ten participants are selected for each group using the CliniCal software in an iterative fashion. A 90% confidence interval is included in the G-power pretest, and the alpha value is set at 0.05. On Kaggle.com, we found a dataset on student education with 66,500 items. We searched through it. The results show that the suggested approach achieved a 94% improvement in accuracy compared to the existing system. In addition, it's safe to say that the disparity between GoogleNet and InceptionNet in predicting student education success, as shown by the SPSS statistical analysis (p=0.002; p<0.05 in the independent model T test). Finally, GoogleNet outperforms InceptionNet in terms of student teaching performance.